qspec

A written plan for building a software feature, using Spec-Driven Development: defining the expected behavior before writing code. It includes inputs, outputs, limits, edge cases, acceptance checks, and matching test outlines.

In plain words
What is it for?
Planning features in the gsd-taskmanager project, including offline use, data syncing, conflicting edits, task dependencies, and database schema changes.
Why use it?
It turns a feature idea into a shared, checkable definition of done. This helps prevent scope creep and makes missing cases and tests visible before implementation.

Command for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/vscarpenter/gsd-task-manager/qspec
Clone the repo
git clone --depth 1 https://github.com/vscarpenter/gsd-task-manager

Made for: Claude Code.

Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 315 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00021 $0.00315
Opus 5 $0.00010 $0.00158
Sonnet 5 $0.00004 $0.00063
Haiku 4.5 $0.00002 $0.00032

Measured 2d ago against content hash 37fd83823626, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qspec scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/qspec.md · 21 lines

What it actually says

Write a spec for the described feature. Follow the Spec-Driven Development standards in coding-standards.md Part 1 and the project conventions in CLAUDE.md.

Feature: $ARGUMENTS

Include every section:

  • Goal — One sentence describing what this does and why it matters for gsd-taskmanager.
  • Inputs / Outputs — Schemas (reference lib/schema.ts Zod types if applicable), data shapes, formats.
  • Constraints — Performance, privacy (local-first IndexedDB), PocketBase sync compatibility, file-size limits (≤350 lines per file, ≤30 lines per function), bundle impact.
  • Edge Cases — Empty inputs, offline mode, sync conflicts, circular task dependencies, concurrent multi-device edits, schema migration scenarios.
  • Out of Scope — Explicit list of what this version does NOT do (prevents scope creep).
  • Acceptance Criteria — Checkable statements that prove correctness. Each AC must map to at least one test.
  • Test Stubs — Empty test function signatures (vitest, behavior-based names like should_persist_task_when_quadrant_changes) mapping to each acceptance criterion.

Save the spec to tasks/spec.md. If a spec already exists there, append a new section dated with today's date rather than overwriting.

Do not write any implementation code. Wait for spec approval before proceeding to /tdd.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 21 lines · 21 tokens per session scan A 37fd83823626

Subscribe to this mod's changes

qspec is a command published in the GitHub repository vscarpenter/gsd-task-manager (24 stars, last pushed 4d ago), licensed MIT. It adds 21 tokens to every session and 315 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.